whale-data

DeFi lending liquidations

defi_liquidations

Read-onlyIdempotent

Lending liquidations from Aave V3 and Morpho Blue on Ethereum, Arbitrum and Base: a third party repaid the debt and seized the collateral, so both wallets are named on every row. A different event from a perp liquidation (see the liquidations tool) and never summed with one. count and total_usd cover exactly the rows returned and the window field states the period those rows span, so the total is never mistaken for a fixed 24h figure. Keyless. Descriptive market data only.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`chain`	No	Restrict to one chain: ethereum, base, arbitrum. Anything else is refused by name rather than answered as nothing happening there. Omit for all of them.
`limit`	No	Max rows returned. Defaults to 50, hard ceiling 200 for everyone and no plan raises it. count and total_usd cover exactly the rows returned, and window states the period those rows span, so neither is a fixed 24h figure.

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No	One line saying what the numbers cover, or why there are none. Read it before reporting any zero as a market reading.
`count`	No	How many rows this reply carries.
`capped`	No	Present only when an argument was cut down to a ceiling. Absent means nothing was clamped, so a smaller number than you asked for is the data and not a limit.
`window`	No	The period the returned rows actually span: from, to and hours.
`matched`	No	How many rows matched the chain filter before the row cap.
`available`	No	False when this lane could not answer: a producer is dark, the pair sits outside this plan, or the argument named something we do not carry. Absent or true means the numbers are a real reading, not a guess.
`total_usd`	No	Dollars across exactly the rows returned. A page sum, not a fixed 24h total: the window field says what period those rows span.
`truncated`	No	True when more rows matched than were returned, so what you have is a page and not the whole set.
`access_note`	No	What this connection could not return and what lifts it. Always pass this on to the user: it is the only place that information appears.
`liquidations`	No	The events, each naming BOTH wallets: the one liquidated and the one that repaid the debt and took the collateral.
`unknown_chain`	No	Set when a chain was named that this lane does not index. Nothing was searched, so this is not no liquidations there.
`chains_covered`	No	The chains this lane indexes.
`protocols_covered`	No	The lending protocols behind these rows.
`duplicates_dropped`	No	How many repeat rows for the same event were removed before counting, so the dollars are not doubled.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedAug 13, 2026

addedInput schema / properties / chain / description

Added value: +"Restrict to one chain: ethereum, base, arbitrum. Anything else is refused by name rather than answered as nothing happening there. Omit for all of them."

addedInput schema / properties / limit / description

Added value: +"Max rows returned. Defaults to 50, hard ceiling 200 for everyone and no plan raises it. count and total_usd cover exactly the rows returned, and window states the period those rows span, so neither is a fixed 24h figure."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "access_note": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "What this connection could not return and what lifts it. Always pass this on to the user: it is the only place that information appears."
+    },
+    "available": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "False when this lane could not answer: a producer is dark, the pair sits outside this plan, or the argument named something we do not carry. Absent or true means the numbers are a real reading, not a guess."
+    },
+    "capped": {
+      "anyOf": [
+        {
+          "additionalProperties": false,
+          "properties": {
+            "applied": {
+              "description": "The value actually used.",
+              "type": "number"
+            },
+            "argument": {
+              "description": "Which argument was cut down, for example limit or hours.",
+              "type": "string"
+            },
+            "by": {
+              "description": "Why it was cut: keyless for the free ceiling, plan_max for a paid ceiling, tool_max for a ceiling no plan raises.",
+              "type": "string"
+            },
+            "max": {
+              "description": "The ceiling that applied.",
+              "type": "number"
+            },
+            "requested": {
+              "description": "The value the caller asked for.",
+              "type": "number"
+            }
+          },
+          "required": [
+            "argument",
+            "requested",
+            "applied",
+            "max",
+            "by"
+          ],
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Present only when an argument was cut down to a ceiling. Absent means nothing was clamped, so a smaller number than you asked for is the data and not a limit."
+    },
+    "chains_covered": {
+      "anyOf": [
+        {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The chains this lane indexes."
+    },
+    "count": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "How many rows this reply carries."
+    },
+    "duplicates_dropped": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "How many repeat rows for the same event were removed before counting, so the dollars are not doubled."
+    },
+    "liquidations": {
+      "anyOf": [
+        {
+          "items": {},
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The events, each naming BOTH wallets: the one liquidated and the one that repaid the debt and took the collateral."
+    },
+    "matched": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "How many rows matched the chain filter before the row cap."
+    },
+    "note": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "One line saying what the numbers cover, or why there are none. Read it before reporting any zero as a market reading."
+    },
+    "protocols_covered": {
+      "anyOf": [
+        {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The lending protocols behind these rows."
+    },
+    "total_usd": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Dollars across exactly the rows returned. A page sum, not a fixed 24h total: the window field says what period those rows span."
+    },
+    "truncated": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "True when more rows matched than were returned, so what you have is a page and not the whole set."
+    },
+    "unknown_chain": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Set when a chain was named that this lane does not index. Nothing was searched, so this is not no liquidations there."
+    },
+    "window": {
+      "anyOf": [
+        {
+          "additionalProperties": {},
+          "propertyNames": {
+            "type": "string"
+          },
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The period the returned rows actually span: from, to and hours."
+    }
+  },
+  "type": "object"
+}

First observedAug 13, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable behavioral context: keyless access, descriptive market data only, and clarifies that 'count' and 'total_usd' cover exactly the returned rows with a 'window' field, avoiding misinterpretation of fixed 24h figures. This exceeds the annotation baseline.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each dense with information: scope, event distinction, and metric semantics. No fluff, front-loaded with the most important purpose, and every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists and annotations cover safety, the description covers scope, event type, chain availability, metric semantics, and alternative tool differentiation. It is complete for a read-only filtered tool with simple parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for both parameters, providing full documentation. The description further clarifies the 'limit' parameter's behavior (defaults, hard ceiling) and the 'chain' parameter's refusal behavior, adding value beyond schema. Baseline 3 is elevated to 4 due to meaningful extra context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('repaid debt and seized collateral') and clearly names resources (Aave V3, Morpho Blue on Ethereum, Arbitrum, Base). It distinguishes from the sibling 'liquidations' tool by explicitly saying it's a different event and never summed with one.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context on what the tool covers (lending liquidations vs perp liquidations) and names the alternative 'liquidations' tool for perp liquidations. It does not explicitly say 'when not to use' beyond the differentiation, but the guidance is specific enough to select correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All whale-data tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?